Routes all generate_content calls through _generate() which retries gemini-3.1-flash-preview then gemini-2.5-pro when primary model hits RESOURCE_EXHAUSTED. Cost tracker records actual model used. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| api/v1 | ||
| core | ||
| lib | ||
| middleware | ||
| migrations | ||
| models | ||
| prompts | ||
| schemas | ||
| services | ||
| tasks | ||
| telemetry | ||
| main.py | ||